Server facts
allvoicelab-mcp
Project
- Author
- allvoicelab
- Repository
- github.com/allvoicelab/AllVoiceLab-MCP
- License
- Not specified
- Category
- Design & Creative
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 62
- Last commit
- Data as of
Tags
- Text To Speech
- ai voice generator
- multilingual dubbing
- speech to text
- subtitle removal
- vocal separation
- voice changer
Overview
Audio production and video localization are the focus of allvoicelab-mcp, which exposes AllVoiceLab services through clients including Claude Desktop and Cursor. Creators can select synthesis models and language-specific voice profiles, generate audio from text, or change an existing recording’s voice without changing its spoken content. Voice conversion includes controls for similarity and background noise removal. A separate cloning tool creates a reusable voice profile from an audio sample, supporting workflows such as audiobook production and narration; access to cloning requires permission.
For localization, the tools translate and dub media, translate TXT or SRT files, and use OCR to extract burned-in subtitles into SRT files or remove them from video. Longer processing jobs use status polling, with task identifiers returned when results are not ready; dedicated helpers check dubbing and subtitle-removal progress and download completed dubbing audio. Subtitle removal may leave stylized or animated text behind. The server communicates over stdio and requires AllVoiceLab credits plus an API key matched to the appropriate regional endpoint. Generated and processed files are saved to local output directories.
allvoicelab-mcp setup notes
- allvoicelab-mcp records stdio only; confirm a network transport upstream before planning remote access.
- allvoicelab-mcp has no recorded license; confirm reuse terms in its repository.